An inspection device inspects of goods that include plural articles that sometimes overlap each other. An X-ray inspection device irradiates goods containing plural articles having a predetermined shape and inspects the goods on the basis of inspection images obtained from radiation that has passed through the goods or radiation that has reflected off the goods. The X-ray inspection device includes a storage component, a learning component, and an inspection component. The storage component stores, as teaching images, at least the inspection images of the goods that are in a state in which the plural articles overlap each other. The learning component acquires, by machine learning using the teaching images stored in the storage component, features relating to the goods that are in a state in which the plural articles overlap each other. The inspection component inspects the goods using the features that the learning component has acquired.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
4. The inspection device according to claim 1, wherein the inspection irradiator further inspects the quantities of the articles contained in the goods.
This invention relates to an inspection device for examining goods, particularly focusing on detecting and quantifying articles within the goods. The device addresses the challenge of accurately identifying and counting items in packages or containers, which is critical for inventory management, quality control, and automated sorting systems. The inspection device includes an irradiator that emits radiation to scan the goods and a detector that captures the resulting signals. The irradiator is designed to not only detect the presence of articles but also measure their quantities, providing detailed information about the contents. The system may use various types of radiation, such as X-rays or other electromagnetic waves, depending on the application. The detector processes the signals to generate data that can be analyzed to determine the number and possibly the type of articles present. This functionality enhances the device's utility in logistics, manufacturing, and security applications where precise inventory tracking is essential. The device may also include additional components, such as a conveyor system to move goods through the inspection area or a data processing unit to analyze the detected signals. The ability to quantify articles improves efficiency and accuracy in automated inspection processes, reducing the need for manual counting and minimizing errors.
5. The inspection device according to claim 4, wherein the learning component acquires the features by machine learning using the teaching images and the quantities of the articles contained in the goods in the teaching images.
The invention relates to an inspection device for analyzing goods, particularly for determining the quantity of articles within packaged goods. The device addresses the challenge of accurately counting or quantifying items in goods, such as packaged products, where visual inspection alone may be insufficient due to overlapping, occluded, or irregularly arranged items. The inspection device includes a learning component that extracts features from teaching images—pre-labeled images of goods with known article quantities. Using machine learning techniques, the learning component trains on these teaching images to learn patterns and relationships between visual features and the actual quantities of articles. This trained model is then applied to new, unlabeled images of goods to predict the quantity of articles contained within. The device may also include an imaging unit to capture images of the goods and a processing unit to analyze the images using the learned features. The machine learning approach improves accuracy by leveraging statistical patterns rather than relying solely on manual or rule-based counting methods. This technology is useful in automated quality control, inventory management, and packaging verification systems.
6. The inspection device according to claim 1, wherein the inspection irradiator acquires a final inspection result of the goods on the basis of a plurality of inspection results comprising first inspection results of the goods in a case where it has used the features acquired by the learning machine and second inspection results of the goods in a case where it has not used the features acquired by the learning machine.
An inspection device is used to evaluate goods, particularly in automated quality control systems. The device addresses the challenge of improving inspection accuracy by leveraging machine learning to enhance detection capabilities. The inspection device includes an irradiator that emits radiation or light to inspect goods, a sensor to detect reflected or transmitted signals, and a learning machine that processes inspection data to identify patterns or features indicative of defects or quality issues. The device operates in two modes: one where it uses features acquired by the learning machine to analyze the goods and another where it does not. The learning machine is trained on historical inspection data to recognize defects or anomalies more accurately. The inspection irradiator generates first inspection results when using the learned features and second inspection results when not using them. The final inspection result is derived by combining these multiple inspection results, allowing the device to cross-validate findings and improve reliability. This dual-mode approach ensures that the system can adapt to different inspection scenarios while maintaining high accuracy. The device is particularly useful in manufacturing, logistics, and quality assurance applications where precise and consistent inspection is critical.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
October 30, 2018
May 7, 2024
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.